Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12557
    Prev
    Next
    INDEX
    Explanations

    words related to savories or savory dishes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.73
     Abp
    -0.62
    __((
    -0.62
    addContainerGap
    -0.60
    kheim
    -0.58
     нах
    -0.57
     JpaRepository
    -0.55
    RectangleBorder
    -0.54
    tvguidetime
    -0.54
    Protobuf
    -0.53
    POSITIVE LOGITS
     Sav
    0.79
    Sav
    0.76
     HttpServlet
    0.71
     sav
    0.62
    SAB
    0.58
     SAB
    0.57
    sab
    0.56
    Sab
    0.55
    ]--;
    0.55
     SAV
    0.52
    Activations Density 0.081%

    No Known Activations